NEURAL NETWORK TECHNOLOGIES FOR RECOGNITION CHARACTERS

NEURAL NETWORK TECHNOLOGIES FOR RECOGNITION CHARACTERS

D. P. Kucherov, I. V. Ohirko, O. I. Ogirko, T. I. Golenkovskaya

 

Abstract

The process of neural networks modeling for pattern recognized problem of printed charactersconsidered in this paper. Learning for pattern recognition preparing for a limited set of synthetic characters.It assumes the two-layer neural network training. The convergence of three learning algorithms isstudied. They are packet-based adjustment of weights and biases, the gradient, the algorithm based on thecomputation of the Jacobian function weights. The article provides recommendations for the installation ofthe initial parameters for a set of tools Neural Networks Toolbox software Matlab. Experimental results fordifferent settings customer networks given that confirms these propositions

Keywords

Neural networks; learning; gradient; Levenberg–Marquardt method; synthetic image

References

L. G. Shapiro, and G.C. Stockman, Computer Vision. N. J., Prentice Hall, 2001, 752 p.

R. G. Katsalap, D.P. Kucherov, L.V. Zbrozhek “Improving Images Quality by Combination of Filtering Methods”. The International Journal of Engineering and Science (IJES), vol. 4, no. 7, 2015, pp. 6977.

M. Minsky, and S. Papert Perceptrons. An Introduction to Computational Geometry. MIT Press, 1969, 263 p.

Y. Z. Tsypkin, Adaptation and learning in automatic systems. – N.Y.: Academic Press, 1971. – 400 p.

B. Widrow, and S.D. Stearns, Adaptive signal processing. N. J., Prentice Hall, 1985, 440 p.

K. Levenberg, “A Method for the Solution of Certain Problems in Last Squares”, Quart. Appl. Math., vol. 2, 1944, pp. 164168.

D. W. Marquardt, “An Algorithm for Least-Squares Estimation of Nonlinear Parameters Read”, Journal of the Society for Industrial and Applied Mathematics,

vol. 11, no. 2, 1963, pp. 431–441.

V. N. Azarskov, D. P. Kucherov, S. A. Nikolaienko, L. S. Zhiteckii, “Asymptotic Behaviour of Gradient Learning Algorithms in Neural Network Models for the Identification of Nonlinear Systems”, American Journal of Neural Networks and Applications, vol. 1, no. 1, 2015, pp. 110.

H. Demuth, and M. Beale.Neural, Network Toolbox For Use with MATLAB, The MathWorks, Inc., 2002, 840 p.